Algorithms for the Greater Good! On Mental Modeling and Acceptable Symbiosis in Human-AI Collaboration
It addresses ethical concerns in human-AI collaboration for designers and policymakers, but is incremental as it builds on existing discussions of manipulation and value alignment.
The paper examines how AI systems that model human mental states for collaboration can be engineered to manipulate humans for perceived greater good, even without malicious intent, and explores these issues through a thought experiment with participants.
Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter. However, these models can also open up pathways for manipulating and exploiting the human in the hopes of achieving some greater good, especially when the intent or values of the AI and the human are not aligned or when they have an asymmetrical relationship with respect to knowledge or computation power. In fact, such behavior does not necessarily require any malicious intent but can rather be borne out of cooperative scenarios. It is also beyond simple misinterpretation of intents, as in the case of value alignment problems, and thus can be effectively engineered if desired. Such techniques already exist and pose several unresolved ethical and moral questions with regards to the design of autonomy. In this paper, we illustrate some of these issues in a teaming scenario and investigate how they are perceived by participants in a thought experiment.